[R] Finding cases in one subset that are closet to another subset

[Peter Flom]

Thanks Chuck

I did not know about that MatchIt.   I will check it out

Peter

-----Original Message-----
>From: Chuck Cleland <ccleland at optonline.net>
>Sent: Dec 2, 2009 3:47 PM
>To: Peter Flom <peterflomconsulting at mindspring.com>
>Cc: r help <r-help at r-project.org>
>Subject: Re: [R] Finding cases in one subset that are closet to another subset
>
>On 12/2/2009 3:01 PM, Peter Flom wrote:
>> Good afternoon
>> 
>> Running R2.10.0 on Windows
>> 
>> I have a data frame that includes (among much else) a factor (In_2006) and a continuous variable (math_3_4).  I would like to find the 2 cases for In_2006 = 0 that are closest to each case where In_2006 = 1.
>> 
>> My data looks like
>> 
>>      In_2006 math_3_4
>>          0     55.1
>>          1     51.6
>>          1     18.1
>>          1     26.6
>>          1     14.1
>>          1      9.6
>>          1     48.9
>>          1     12.9
>>          0     63.0
>>          0     51.8
>> 
>> etc. for several hundred rows.
>> 
>> I would like a new data frame that has all the cases where In_2006 = 1, and those cases of In_2006 that are closest to those cases
>
>Hi Peter:
>
>  How about using one of the various matching packages (MatchIt,
>optmatch, Matching)?  For example, something like this:
>
>
>DF <- data.frame(X = rbinom(200, 1, .1), Y = runif(200))
>
>library(MatchIt)
>
>DF.match <- matchit(X ~ Y, data=DF, method='optimal', ratio=2)
>
>DF[c(rownames(DF.match$match.matrix), c(DF.match$match.matrix)),]
>
>
>hope this helps,
>
>Chuck
>
>> Thanks in advance
>> 
>> Peter
>> 
>> Peter L. Flom, PhD
>> Statistical Consultant
>> Website: www DOT peterflomconsulting DOT com
>> Writing; http://www.associatedcontent.com/user/582880/peter_flom.html
>> Twitter:   @peterflom
>> 
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code. 
>
>-- 
>Chuck Cleland, Ph.D.
>NDRI, Inc. (www.ndri.org)
>71 West 23rd Street, 8th floor
>New York, NY 10010
>tel: (212) 845-4495 (Tu, Th)
>tel: (732) 512-0171 (M, W, F)
>fax: (917) 438-0894


Peter L. Flom, PhD
Statistical Consultant
Website: www DOT peterflomconsulting DOT com
Writing; http://www.associatedcontent.com/user/582880/peter_flom.html
Twitter:   @peterflom